LAB #2107 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.0% to 32.8% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.0% to 32.8% (+0.8pp, n=1039) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter to the 10 live trades above would have blocked the three XAUUSD SHORT losses (entries 4048.74, 4051.79, 4066.35) and likely the GBPUSD SHORT loss (1.34508), while keeping the four wins and the open USDJPY trade. That would flip the live window from 4W/5L (44% win rate) to roughly 4W/1L (80% win rate) — a massive PnL improvement, but the sample is tiny and dominated by one asset class (XAUUSD) that may have been in a specific regime. The +0.8pp backtest gain is directionally consistent but the live effect here is exaggerated due to selection bias in the window. OVER-TIME PROJECTION: Over 3–6 months, the filter would likely reduce trade frequency (blocking ~15–20% of signals) and shift the book toward cleaner trends, but the +0.8pp win-rate edge is marginal Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com